Abstract:Runtime monitoring is essential to ensure the safety of ML applications in safety-critical domains. However, current research is fragmented, with independent methods emerging from different communities. In this paper, we propose a unified framework categorising runtime monitoring approaches into three distinct types: Operational Design Domain (ODD) monitoring, which ensures compliance with expected operating conditions; Out-of-Distribution (OOD) monitoring, which rejects inputs that deviate from the training data; and Out-of-Model-Scope (OMS) monitoring, which detects anomalous model behaviour based its internal states or outputs. We demonstrate the benefits of this categorization with a dedicated experiment on an aeronautical safety-critical application: runway detection during landing. This framework facilitates design of monitoring activities, with complementary categories of monitors, and enables evaluation and comparison of different monitors using common, safety-oriented metrics.
| Comments: | 15 pages, 5 figures, 3 tables, submitted to ICPR 2026 |
| Subjects: | Machine Learning (cs.LG) |
| Cite as: | arXiv:2604.26411 [cs.LG] |
| (or arXiv:2604.26411v1 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2604.26411 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Mathieu Dario [view email]
[v1]
Wed, 29 Apr 2026 08:24:39 UTC (823 KB)